© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 28095
    Prev
    Next
    INDEX
    Explanations

    references to gender and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/1-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    69
    +0.13
    0.7%
    324
    +0.12
    0.6%
    112
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    293
    +0.13
    0.00
    441
    +0.12
    0.00
    236
    +0.11
    0.00
    Negative Logits
    oretic
    -1.79
    worth
    -1.63
     thereof
    -1.59
     defenses
    -1.59
    keit
    -1.56
    ing
    -1.54
    **).
    -1.53
    aceae
    -1.51
     therefrom
    -1.50
    enberg
    -1.50
    POSITIVE LOGITS
    pin
    1.60
     Diabetes
    1.46
    pril
    1.45
     WARN
    1.42
     notch
    1.40
    aukee
    1.33
     NCAA
    1.32
     Hollow
    1.32
     INS
    1.32
     ESPN
    1.31
    Activations Density 0.000%

    No Known Activations